Presentation | 2008-11-27 Automatic Segmentation of Human Motion Patterns using Predictor RNN Tong NIU, Yoshio IWAI, Masahiko YACHIDA, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | Recently, diversity of crimes has become a major social problem, calling for reinforcements in security systems. The objective of the author's research is to create a system that automatically detects unknown behaviors as exceptions. Such systems require retraining of the whole system when supplementing a new behavior into the model. In this research, the authors aim to segment the behaviors, based on predictability of the recurrent neural network, for retraining only the sub-model for supplementation. In this paper, the authors present the results of the segmentation experiment using proposed method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | |
Paper # | PRMU2008-120,MVE2008-69 |
Date of Issue |
Conference Information | |
Committee | MVE |
---|---|
Conference Date | 2008/11/20(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Media Experience and Virtual Environment (MVE) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Automatic Segmentation of Human Motion Patterns using Predictor RNN |
Sub Title (in English) | |
Keyword(1) | |
1st Author's Name | Tong NIU |
1st Author's Affiliation | Graduate School of Engineering Science, Osaka University() |
2nd Author's Name | Yoshio IWAI |
2nd Author's Affiliation | Graduate School of Engineering Science, Osaka University |
3rd Author's Name | Masahiko YACHIDA |
3rd Author's Affiliation | Faculty of Information Science and Technology, Osaka Institute of Technology |
Date | 2008-11-27 |
Paper # | PRMU2008-120,MVE2008-69 |
Volume (vol) | vol.108 |
Number (no) | 328 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |